Step 1
Collect the metrics the merchant actually reviews, the source field and filter behind each, the refresh cadence, the reporting window and the currency and timezone that apply to every tile.
A merchant wants one dashboard for revenue questions, but each tile comes from a different export, so no two tiles agree on what a metric means. In this case, the immediate task is to create a sales dashboard with clear metric definitions. The workflow should produce a definition and source field per tile, each figure rebuildable from orders and returns.
First replace every [bracketed] placeholder with real store scope and constraints, then add any actual records or data you have, and paste it into your preferred AI assistant or Spark agent. Spark will follow this page's workflow to produce structured output and verification steps.
Act as a Shopify operations specialist.
Help me create a sales dashboard with clear metric definitions.
My store context is [describe the business, products and target audience].
My scope is [specify the affected products, pages, customers or reporting period]. Use these inputs: [the metrics the merchant actually reviews, the source field and filter behind each, the refresh cadence, the reporting window, and the currency and timezone applied to every tile]. Write one definition per tile naming the source field, the order statuses counted, the date field and the aggregation, and drop or merge any tile whose number cannot be rebuilt from the orders and returns available rather than leaving it sourced from a separate export nobody can reproduce.
Return a sales report with definitions and the rebuild check for every tile for the specified task.
Show the relevant evidence or before-and-after examples and explain how I can verify the result.
If essential data is missing, ask for it and mark unsupported conclusions as unknown.
Do not invent metrics, product claims or customer facts.
For any publication, message, account or store change, use only connected tools within my explicitly authorized scope and report success only after verification; otherwise provide the draft or proposed steps.Split the work into input, judgment, and deliverable phases. Verify each step's output before moving to the next.
Collect the metrics the merchant actually reviews, the source field and filter behind each, the refresh cadence, the reporting window and the currency and timezone that apply to every tile.
Write one definition per tile naming the source field, the order statuses counted, the date field and the aggregation, and drop or merge any tile whose number cannot be rebuilt from the orders and returns available rather than leaving it sourced from a separate export nobody can reproduce.
Deliver the dashboard specification with the definition, source field, refresh time and owner per tile, then verify each figure by rebuilding it from orders and returns and recording the difference, and mark tiles whose refresh lags the reporting window.
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Only the ones the merchant actually reviews. Each extra tile dilutes attention and adds a definition to maintain, and an unreviewed tile that later disagrees with another export costs more trust than the tile ever returned in usefulness.
Yes. Naming the source field, the status filter and the date field lets a reader rebuild the number when it is questioned. A tile without that annotation is a picture of a number rather than a metric, and it cannot survive a change of owner.
Reconcile them rather than averaging. Disagreement usually means different status filters or date fields sit behind the same word, so the two definitions are compared side by side and one is chosen for the shared term, with the other renamed.
Start with scenarios under the same topic, then expand into cross-topic matches suggested by similarity.
Ciwi Spark builds Shopify-native AI tools and agents around the workflows merchants actually run: research, ads, translation, and customer support. Stop rewriting the same prompts by hand.